Date of Award

2025

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Mathematical Sciences

Committee Chair

Satyaki Roy

Committee Member

Dongsheng Wu

Committee Member

Summer Atkins

Committee Member

Jennifer Bail

Research Advisor

Satyaki Roy

Subject(s)

Medical care--Decision making--Mathematical models, Hospitals--Administration--Data processing, Reinforcement learning

Abstract

This thesis addresses the challenge of optimizing patient referrals in healthcare systems by integrating clinical needs, geographic proximity, and dynamic infection risk. Healthcare referral networks (HRNs), which capture patient transfers between hospitals, serve as the foundation of the study. First, a recommendation algorithm is developed to assign patients by jointly considering clinical compatibility and logistical considerations like travel distance, striking a balance between quality and accessibility. Building on this, a reinforcement learning framework is proposed to dynamically adjust referral strategies for vulnerable patients by incorporating the evolving risk of hospital-acquired infections. Finally, long-term planning is explored through methods that recommend future hospital placements based on projected population demand and referral patterns. These approaches are validated on real-world HRN datasets using metrics of clinical match, efficiency, and infection-aware allocation. Overall, they open up a data-driven route to resilient, equitable, and adaptive referral systems.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.